Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,861 indexed, measured the same four ways as everything else here.
legendtkl/agentic-skill-router
Skill Claude CodeCodex
Comprehensive guide for implementing Fullstory's User Properties API (setProperties with type 'user') for web applications. Teaches proper property naming, type handling, incremental updates, and special fields (displayName, email). Includes detailed good/bad examples for CRM integration, progressive profiling, and…
Skill Claude CodeCodex
A guide to using Tushare, a financial-data service, including setting its access token and creating its Pro interface.
Skill Claude CodeCodex
Create, edit, and review ai-harness public documentation with BetterDoc's claim-first, evidence-aware workflow. Use for README and website copy, quickstarts, reference docs, architecture and ADRs, security and assurance docs, runbooks, migration guides, changelogs, release notes, PR summaries, or any other public…
Skill Claude CodeCodex
Primes an artefact-producing agent to separate what it intended, what it materialised, what it re-checked, and what remains unverified before it reports completion. Load for build-class tasks (code generation, evidence-pack emission, tool-wrapper generation, implementation work whose claims can be re-tested against…
Skill Claude CodeCodex
Use when operating the CubeStack platform — creating, inspecting or connecting to ai.cubestack.io resources (DevEnvironment / InferenceService / ModelVersion / InferenceRuntimeProfile). Gives the generated CRD map (crd-reference.md) plus a known-good DevEnvironment manifest and usage guidance, so you do not guess…
Skill Claude CodeCodex
THE primary entry point for all SDLC and PDLC work. Use when user mentions: "SDLC", "PDLC", "build this feature", "implement the spec", "run the SDLC loop", "go back to SDLC", "continue implementation", "product context", "document this feature", "launch prep", or any spec-related work (requirements, design, tasks…
lesleslie/jinja2-async-environment
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "crackerjack", hosted remotely at localhost, as configured in lesleslie/jinja2-async-environment. Needs 4 environment variables to run.
Bilal140202/the-lord-of-the-skills
Skill Claude CodeCodex
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…
MCP server Claude CodeCodexCursor +2
One of 2 in mcp.json
MCP server "souschef" as configured in kpeacocke/souschef. Runs souschef.server with /workspaces/souschef/.venv/bin/python. Needs 1 environment variable to run.
Skill Claude CodeCodex
Give this NanoClaw's agents persistent, governed memory from an mwe-mcp server. Every turn is remembered and recalled mechanically, per speaker, with the built-in memory tree switched off and no session carried between turns.
Skill Claude CodeCodex
Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.
Skill Codex
Turn long-form content, reports, structured notes, concepts, processes, and data into polished infographic images or cohesive infographic series. Use when the user asks to summarize, visualize, explain, structure, or convert content into an infographic, visual brief, data poster, explainer, process graphic, or…
Skill Claude CodeCodex
A natural-language interface for Ansys HFSS, an engineering program used to model and simulate antennas and microwave structures. It uses an HFSS agent server to create models, set simulation details, and run analyses.
Skill Claude CodeCodex
Create high-quality architecture diagrams for any project with official SVG logos and clean editorial styling. Use when asked to visualize project architecture, generate a system architecture diagram, or create an arch diagram.
Skill Claude CodeCodex
A set of instructions for adding and repairing datasets in kpubdata, a project that describes public data APIs with specification files. It covers recording real API responses, replaying examples, validating schemas, and updating documentation.
Skill Claude CodeCodex
Build or review substantial full-stack and product-facing UI work with evidence-bound architecture, production, accessibility, interaction, and ethical UX gates. Skip trivial edits and non-product documentation.
Skill Claude CodeCodex
An exploratory browser test that uses a real browser and a first-time-user perspective to find where people get stuck or do not understand a web product. Each finding includes the text seen on screen and screenshot evidence, ordered by how much it blocks progress.
Skill Claude CodeCodex
Activates Flaiwheel knowledge tools for any coding, debugging, architecture, or documentation task. Searches the knowledge base before writing code, documents fixes after resolving bugs, and saves session context at the end of every conversation.
Skill Claude CodeCodex
Build, run, validate, and schedule browser automations with Figranium. Use for rendered websites, repeatable browser workflows, extraction, downloads, forms, and tasks that need real browser interaction.
Skill Claude CodeCodex
Diagnose an AIQSA installation using bounded application logs and process state. Use for failed or stuck runs, Stop and timeout questions, provider/tool errors, background jobs, startup failures, and preparing a sanitized bug report. Collect existing evidence without changing the installation.
Skill Claude CodeCodex
Integrate Sinch In-App Voice and Video SDK for real-time calling in Android, iOS, or JavaScript apps. Use when the user mentions In-App Calling, VoIP integration, WebRTC with Sinch, app-to-phone calling, video calling, or building voice/video features in a mobile or web app.
Skill Claude CodeCodex
Decides whether delegating work to a subagent is worth its cost, picks the right agent shape (fork vs. fresh vs. no delegation), and scopes the dispatch so it doesn't spend more context than it saves. Use when an AI coding agent is about to spawn a subagent, fork itself, or launch a parallel wave of agents, and needs…
MCP server Claude CodeCodexCursor +2
MCP server "plaud" as configured in Gunnarguy/PlaudBlender. Runs locally from the @plaud-ai/mcp npm package.
Skill Claude CodeCodex
A procedure for using clum, a remote Linux operations platform that runs commands through a secure proxy rather than direct SSH. It also describes how to inspect systems, investigate failures, compare solutions, and review incidents.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: